Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hermes-labs-ai/hermeneutic --skill hermeneutic-gategit clone --depth 1 https://github.com/hermes-labs-ai/hermeneuticWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate)<a href="https://agentmods.dev/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate"><img src="https://agentmods.dev/badge/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate"><img src="https://agentmods.dev/badge/skills/hermes-labs-ai/hermeneutic/hermeneutic-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00350 |
| Opus 5 | $0.00023 | $0.00175 |
| Sonnet 5 | $0.00009 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
hermeneutic-gate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Hermeneutic gate
Use the installed hermeneutic CLI as a cheap, zero-LLM pre-flight check for
assistant drafts. It catches fixed English surface patterns associated with
completion overclaiming, relayed authority, unhedged certainty, scope
expansion, and unsupported quality adjectives.
Workflow
-
Identify the exact draft that is about to be sent.
-
Run
hermeneutic gatewith the draft on standard input, for example:printf '%s' "$DRAFT" | hermeneutic gate -
Inspect the printed verdict as well as the exit code. A low-severity
RISKis advisory and exits 0; medium- and high-severityRISKexits 1. -
If the draft is held, add the missing evidence, hedge the claim, or remove the unverifiable text before sending it.
The gate is advisory and does not edit the draft or call an LLM. Do not treat a pass as proof that a draft is correct, complete, safe, or free of novel drift. It checks English surface patterns only and does not replace human review.
Use this skill especially when the draft contains numeric claims, says that work is done or shipped, uses words such as “every” or “always”, or summarizes work completed by another agent.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 37 lines · 46 tokens per session scan A b9d6625a58ec
hermeneutic-gate is a skill published in the GitHub repository hermes-labs-ai/hermeneutic (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 350 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other skills, from other repositories
deepeval
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; send results to Confident AI…
deepeval-otel
Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory. TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans from an LLM app, agent, RAG pipeline, or chatbot to Confident AI; configure the Confident AI OTLP endpoint; set confident.span. or confident.trace. attributes…
deepeval-tracing
Instrument an AI application with DeepEval's native tracing so its behavior is visible in Confident AI. TRIGGER when the user wants to add DeepEval tracing or @observe to an LLM app, agent, RAG pipeline, or chatbot; wire a framework, model-provider, or vector-database integration (LangGraph, LangChain, OpenAI Agents…
tracely
Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…
benchmark-radar
Find, inspect, and check AI benchmark records with the Benchmark Radar CLI. Use when a request needs benchmark discovery, details, recent Radar evidence, or local data health; do not assume why the user needs the results.
deslop
Audit or apply evidence-backed, test-first subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external behavior. Invoke explicitly for semantic simplification, not generic refactoring.